We partnered up with Adaptive Adventures and BAE Systems to develop a solution aimed at enhancing the safety of veterans with traumatic injuries, such as limb loss or paralysis. These veterans often lose the ability to sense temperature in affected limbs, which can lead to severe health risks like frostbite or overheating during physical activities. We developed a temperature sensor that can seamlessly communicate to a mobile application. This will monitor the user’s temperature and provide real-time alerts to the user if the user's temperature goes into harmful thresholds.

Our project created a program that allows the professor that oversees the capstone program within the Chandra Family Department of Electrical and Computer Engineering to quickly and effectively assign students into capstone projects. The program takes students who have project preferences and industry projects that have skills requirements and groups them accordingly while making balanced teams that meet the requirements for those projects. The program also accounts for students who wished to opt-out of projects with non-disclosure agreements or intellectual property agreements.

Biodigesters are frequently employed by refugee camps and temporary settlements to break down human waste in places lacking existing plumbing infrastructure. Our project aims to develop a solar-powered temperature regulation system for biodigesters that enhances the efficiency of waste breakdown while maintaining the ability to operate off-grid. 

Team Members:

Sarah Go
Twinkle Khanna
Rishi Nippani
Abhishek Rao
Yuyao (Andrew) Wang

Our project involves the development of a programmable camera system integrated with a custom-designed app to explore the correlation between physical and mental health. The core of the system is a smart camera that captures physical data such as social interaction and screen time. This data, along with user input, is then analyzed using advanced algorithms to infer physical health indicators and emotional states. The companion app serves as an interactive platform where users can view their health metrics, receive personalized insights, and access wellness recommendations.

The proposed senior design project centers on two tasks. The first is prototyping of a federated learning framework that deploys in-network data aggregation. This would involve working with a publicly available network prototyping platform developed by the National Science Foundation (NSF) to enable experiments that explore limitations of networking infrastructure. Such experiments would help users learn how to process and exchange data amongst the network nodes, ultimately enabling efficient implementations of the FL algorithm.

Generative AI is a growing method for improving the intelligence of machines. This means the application will have the ability to generate new content rather than just evaluating existing data. This project explored existing text-to-speech models, leveraging the real-time training aspects of them. This technology is useful in many contexts, such as when an individual’s speech is impaired due to disability or sickness.

Every day, video conferencing apps connect individuals all over the world. Eye contact is a key element for establishing and maintaining a genuine connection between individuals, but this is largely lost when using a webcam. To solve this problem, we developed an open-source and extremely lightweight gaze correction model that uses machine learning to make the user's eyes appear to be directed at their web camera, creating the illusion of eye-to-eye contact. It can run without a dedicated GPU. To showcase the model, we created a web conferencing app centered around a user's eye gaze.

Current CPUs are extremely complex with intricate microarchitectural features such as advanced branch predictors. However, understanding the precise impact of these features on performance can be challenging.

Our project is focused on leveraging gas-sensing technology to develop an innovative solution for the critical environmental issue of gas leakages in pipelines. These gas leaks, if active, can have significant negative effects on the environment, such as causing climate change and smog. By creating a sophisticated sensor network and a robust sensor data analysis framework, we aimed to accurately monitor and report gas concentrations in real-time, enabling swift identification of leaks within a defined radius.

Deploying autonomous agents (AGs) on edge devices to explore unfamiliar environments is challenging. Indeed, when deploying multiple AGs to navigate unknown environments, a major challenge arises because pre-trained models for navigation, such as monocular depth estimation, may not perform well in such new settings. Therefore, it is essential to continuously adapt the pre-trained models to the new environment through ongoing learning processes. Additionally, the AGs need to make real-time predictions to navigate effectively in the new environment.